Home › Directory › Model Hosting & Inference › VLLM (high-performance LLM inference)
VLLM (high-performance LLM inference)
A high-throughput and memory-efficient inference and serving engine for LLMs
Visit VLLM (high-performance LLM inference)Docs
| Category | Model Hosting & Inference |
|---|---|
| Authentication | No auth |
| Pricing | Free |
| Website | https://github.com/vllm-project/vllm |
| Docs | https://github.com/vllm-project/vllm/tree/main/docs |
| Last checked | 2026-10-14 |
| As JSON | /api/v1/directory/vllm-high-performance-llm-inference.json |
Information is summarised in our own words and may be out of date; check the vendor's site for current terms and prices. Not affiliated with VLLM (high-performance LLM inference). Suggest a correction.
More in Model Hosting & Inference
Together AI
Serverless and dedicated inference for open-source models, plus fine-tuning and image generation.
Fireworks AI
Fast hosted inference for open models with function calling, JSON mode and fine-tuning support.
Hugging Face Inference Providers
Unified access to models from the Hugging Face Hub, served by several inference partners behind one token.
Replicate
Run community and official models, mostly image, video and audio, with a simple prediction API and per-second billing.